search

lm-sys / FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Apache License 2.0
35.53k stars 4.36k forks source link

[Feat Request] Adding 72b/110b llava to multimodal chatbot areana #3406

Open Luodian opened 2 weeks ago

Luodian commented 2 weeks ago

I saw chatbot areana had the multimodal version.

Could we add 72B/110B LLaVA-Next model to it? Or we already had it?

image

We really wish to see the performance on real arena!

HF Collections: https://huggingface.co/collections/lmms-lab/llava-next-6623288e2d61edba3ddbf5ff

I integrated them in SGLang so I think it could be easy to launch it as a backend service. https://github.com/sgl-project/sglang/blob/main/examples/usage/llava/http_qwen_llava_test.py